HumanCompatibleAI / tensor-trustLinks
A prompt injection game to collect data for robust ML research
☆62Updated 4 months ago
Alternatives and similar repositories for tensor-trust
Users that are interested in tensor-trust are comparing it to the libraries listed below
Sorting:
- ☆72Updated 7 months ago
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".☆49Updated 8 months ago
- PAL: Proxy-Guided Black-Box Attack on Large Language Models☆51Updated 10 months ago
- TAP: An automated jailbreaking method for black-box LLMs☆173Updated 6 months ago
- Dataset for the Tensor Trust project☆42Updated last year
- [ICML 2024] COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability☆152Updated 6 months ago
- ☆66Updated 11 months ago
- Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives☆69Updated last year
- [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models☆76Updated last month
- ☆34Updated 7 months ago
- [NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.☆158Updated 2 months ago
- Whispers in the Machine: Confidentiality in Agentic Systems☆39Updated last month
- ☆68Updated last month
- Implementation of BEAST adversarial attack for language models (ICML 2024)☆88Updated last year
- The official repository of the paper "On the Exploitability of Instruction Tuning".☆64Updated last year
- Attack to induce LLMs within hallucinations☆156Updated last year
- ☆89Updated 2 months ago
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆51Updated 2 months ago
- ☆36Updated last month
- Code repo for the paper: Attacking Vision-Language Computer Agents via Pop-ups☆33Updated 6 months ago
- ☆29Updated 10 months ago
- General research for Dreadnode☆23Updated last year
- A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.☆69Updated last year
- This repository provides a benchmark for prompt Injection attacks and defenses☆232Updated 3 weeks ago
- The jailbreak-evaluation is an easy-to-use Python package for language model jailbreak evaluation.☆23Updated 7 months ago
- Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers☆52Updated 10 months ago
- [ICLR'24 Spotlight] A language model (LM)-based emulation framework for identifying the risks of LM agents with tool use☆145Updated last year
- [ICLR 2025] Dissecting adversarial robustness of multimodal language model agents☆91Updated 4 months ago
- ☆175Updated last year
- TaskTracker is an approach to detecting task drift in Large Language Models (LLMs) by analysing their internal activations. It provides a…☆56Updated 3 months ago